Related papers: Data Scaling in OBDA Benchmarks: The VIG Approach
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms,…
Unsupervised multi-source domain adaptation (UMDA) leverages labeled data from multiple source domains to generalize to an unlabeled target. While federated UMDA addresses privacy by avoiding raw data sharing, existing methods scale poorly…
Spatial data is ubiquitous in our data-driven society. The Logic Programming community has been investigating the use of spatial data in different settings. Despite the success of this research, the Geographic Information System (GIS)…
Modern data collection in many data paradigms, including bioinformatics, often incorporates multiple traits derived from different data types (i.e. platforms). We call this data multi-block, multi-view, or multi-omics data. The emergent…
In this paper we present a novel method to connect data on the visualization level. In general, visualizations are a dead end, when it comes to reusability. Yet, users prefer to work with visualizations as evidenced by WYSIWYG editors. To…
Video data is increasingly used alongside conventional data for interactive data exploration, necessitating interfaces for exploring and presenting mixed-modality data. However, integrating video into visualizations remains difficult due to…
Instance segmentation is a problem of significance in computer vision. However, preparing annotated data for this task is extremely time-consuming and costly. By combining the advantages of 3D scanning, reasoning, and GAN-based domain…
A wide range of code intelligence (CI) tools, powered by deep neural networks, have been developed recently to improve programming productivity and perform program analysis. To reliably use such tools, developers often need to reason about…
Recognized for fostering innovation and transparency, driving economic growth, enhancing public services, supporting research, empowering citizens, and promoting environmental sustainability, High-Value Datasets (HVD) play a crucial role in…
Open-source software (OSS) vulnerabilities are increasingly prevalent, emphasizing the importance of security patches. However, in widely used security platforms like NVD, a substantial number of CVE records still lack trace links to…
We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value function. Inspired by the splitting approach in numerical…
Supervised learning algorithms are nowadays successfully scaling up to datasets that are very large in volume, leveraging the potential of in-memory cluster-computing Big Data frameworks. Still, massive datasets with a number of…
Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for…
Sustainable Development Goals (SDGs) bring together the diverse development community and provide a clear set of development targets for 2030. Given a large number of actors and initiatives related to these goals, there is a need to have a…
An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to…
Current generation of Internet-based services are typically hosted on large data centers that take the form of warehouse-size structures housing tens of thousands of servers. Continued availability of a modern data center is the result of a…
Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although…
In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify query-specific regions in text-rich document images.…
Modern data centers that provide Internet-scale services are stadium-size structures housing tens of thousands of heterogeneous devices (server clusters, networking equipment, power and cooling infrastructures) that must operate…
Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration. We advance and refine such methods to infer compute-optimal model shapes, such as width and depth, and…